INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     housing
    -0.09
     flank
    -0.08
    Housing
    -0.08
    γρά
    -0.08
     Libert
    -0.08
     woningen
    -0.07
     unstable
    -0.07
     proprietary
    -0.07
    maatschapp
    -0.07
     inf
    -0.07
    POSITIVE LOGITS
    0.08
     fetus
    0.08
    0.08
    42
    0.08
    .bold
    0.08
     순간
    0.08
     tele
    0.07
     fetal
    0.07
    0.07
    очка
    0.07
    Act Density 0.004%

    No Known Activations